Resnet50源码-tensorflow+keras详细解析

Resnet50源码-tensorflow解析

原理解析：何凯明论文PPT-秒懂原理

项目地址：Resnet50源码

参考keras中的源码进行解析

先加载一些库的文件

from __future__ import print_function

import numpy as np
import warnings

from keras.layers import Input
from keras import layers
from keras.layers import Dense
from keras.layers import Activation
from keras.layers import Flatten
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import GlobalMaxPooling2D
from keras.layers import ZeroPadding2D
from keras.layers import AveragePooling2D
from keras.layers import GlobalAveragePooling2D
from keras.layers import BatchNormalization
from keras.models import Model
from keras.preprocessing import image
import keras.backend as K
from keras.utils import layer_utils
from keras.utils.data_utils import get_file
from keras.applications.imagenet_utils import decode_predictions
from keras.applications.imagenet_utils import preprocess_input
from keras.applications.imagenet_utils import _obtain_input_shape
from keras.engine.topology import get_source_inputs

然后添加预训练的权重（采用网上的resnet50进行举例）

WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels.h5'
WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'

简单了解下残差网络的原理图

然后我们可以开始定义结构的主体，首先定义identity(x)

def identity_block(input_tensor, kernel_size, filters, stage, block):
    """The identity block is the block that has no conv layer at shortcut.
    # Arguments
        input_tensor: input tensor  #输入变量#
        kernel_size: defualt 3, the kernel size of middle conv layer at main path #卷积核的大小#
        filters: list of integers, the filterss of 3 conv layer at main path  #卷积核的数目#
        stage: integer, current stage label, used for generating layer